Nestor offers a modular architecture to assemble AI agents that maintain conversation state, invoke external tools, and customize processing pipelines. Key features include session-based memory stores, a registry for tool functions or plugins, flexible prompt templating, and unified LLM client interfaces. Agents can execute sequential tasks, perform decision branching, and integrate with REST APIs or local scripts. Nestor is framework-agnostic, enabling users to work with OpenAI, Azure, or self-hosted LLM providers.